Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to progression, action, or development

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey the concept of gaining or receiving something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gardens
    -0.58
    SPONSORED
    -0.58
     annex
    -0.57
     albeit
    -0.57
    velt
    -0.57
     Archdemon
    -0.56
    scape
    -0.55
     Britann
    -0.55
     commanding
    -0.55
     Austral
    -0.55
    POSITIVE LOGITS
     rid
    1.34
    tin
    0.99
    cloneembedreportprint
    0.99
     acquainted
    0.97
    acqu
    0.90
     bored
    0.89
     distracted
    0.88
     married
    0.87
     sucked
    0.86
    TING
    0.85
    Act Density 0.120%

    No Known Activations